{"id":"https://openalex.org/W4375868828","doi":"https://doi.org/10.1109/icassp49357.2023.10095529","title":"Low Precision Representations for High Dimensional Models","display_name":"Low Precision Representations for High Dimensional Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868828","doi":"https://doi.org/10.1109/icassp49357.2023.10095529"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095529","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032741006","display_name":"Rajarshi Saha","orcid":"https://orcid.org/0000-0002-7863-9811"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajarshi Saha","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001436196","display_name":"Mert Pilanc\u0131","orcid":"https://orcid.org/0000-0002-0870-9992"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mert Pilanci","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074116801","display_name":"Andrea Goldsmith","orcid":"https://orcid.org/0000-0001-5686-800X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea J. Goldsmith","raw_affiliation_strings":["Stanford University","Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05642669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"97","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173211574554443},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.6790828704833984},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6777371168136597},{"id":"https://openalex.org/keywords/switchover","display_name":"Switchover","score":0.6062612533569336},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.6039206385612488},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5123823285102844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46451038122177124},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46041637659072876},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.45936697721481323},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43382638692855835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42811501026153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3753146529197693},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3668176531791687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3434247374534607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1912176012992859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173211574554443},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.6790828704833984},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6777371168136597},{"id":"https://openalex.org/C124200919","wikidata":"https://www.wikidata.org/wiki/Q2373346","display_name":"Switchover","level":2,"score":0.6062612533569336},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6039206385612488},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5123823285102844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46451038122177124},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46041637659072876},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.45936697721481323},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43382638692855835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42811501026153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3753146529197693},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3668176531791687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434247374534607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1912176012992859},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095529","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2033787551","https://openalex.org/W2040871222","https://openalex.org/W2112038498","https://openalex.org/W2119144962","https://openalex.org/W2198959656","https://openalex.org/W2903397918","https://openalex.org/W2913668833","https://openalex.org/W2964336134","https://openalex.org/W3120740533","https://openalex.org/W3137147200","https://openalex.org/W3164441165","https://openalex.org/W4210968171","https://openalex.org/W4221154844","https://openalex.org/W4229574485","https://openalex.org/W6675111496","https://openalex.org/W6677580257","https://openalex.org/W6687799339","https://openalex.org/W6755737014","https://openalex.org/W6763621396","https://openalex.org/W6810151809","https://openalex.org/W6840899668"],"related_works":["https://openalex.org/W2385368614","https://openalex.org/W2391729463","https://openalex.org/W2369951470","https://openalex.org/W2368126447","https://openalex.org/W2379248043","https://openalex.org/W2370187656","https://openalex.org/W2367027673","https://openalex.org/W2097736318","https://openalex.org/W3217437743","https://openalex.org/W2364199420"],"abstract_inverted_index":{"The":[0,55],"large":[1],"memory":[2],"footprint":[3],"of":[4,28,62,116,135],"high":[5],"dimensional":[6],"models":[7],"require":[8],"quantization":[9,71],"to":[10,51,102,107,144],"a":[11,30,35,40,52,104,121],"lower":[12,146],"precision":[13],"for":[14,126],"deployment":[15],"on":[16,84],"resource":[17],"constrained":[18,87],"edge":[19],"devices.":[20],"With":[21],"this":[22],"motivation,":[23],"we":[24],"consider":[25],"the":[26,46,59,63,85,97,108,114,132,145],"problems":[27],"learning":[29],"(i)":[31],"linear":[32,37],"regressor,":[33],"and":[34,44,66],"(ii)":[36],"classifier":[38],"from":[39],"given":[41],"training":[42],"dataset,":[43],"quantizing":[45,120],"learned":[47],"model":[48],"parameters":[49],"subject":[50],"pre-specified":[53],"bit-budget.":[54],"error":[56,75],"metric":[57],"is":[58],"prediction":[60],"risk":[61,89,105],"quantized":[64],"model,":[65],"our":[67,93,117,136],"proposed":[68,94,137],"randomized":[69],"embedding-based":[70],"methods":[72],"attain":[73],"near-optimal":[74],"while":[76],"being":[77],"computationally":[78],"efficient.":[79],"We":[80,111],"provide":[81],"fundamental":[82],"bounds":[83],"bit-budget":[86],"minimax":[88],"that,":[90],"together":[91],"with":[92],"algorithms,":[95],"characterize":[96],"minimum":[98],"threshold":[99],"budget":[100],"required":[101],"achieve":[103],"comparable":[106],"unquantized":[109],"setting.":[110],"also":[112],"show":[113,131],"efficacy":[115],"strategy":[118],"by":[119],"two-layer":[122],"ReLU":[123],"neural":[124],"network":[125],"non-linear":[127],"regression.":[128],"Numerical":[129],"simulations":[130],"improved":[133],"performance":[134],"scheme":[138],"as":[139,141],"well":[140],"its":[142],"closeness":[143],"bound.":[147]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}